目录 / EvalGate
MCP
鉴权未知
未评级
已上架
EvalGate
Organization-scoped, read-only access to EvalGate project, evaluation, run, and baseline evidence. Public protocol and tool-schema discovery; product tool execution requires scoped authentication. Documentation: https://www.evalgate.com/docs/platform/mcp-integration. Portable Agent Skills and MCP configuration: https://github.com/evalgate/skills (separate from the hosted server implementation).
该来源不提供完整文件导出(国内平台多为平台内托管),仅存元数据与原链
模型生成摘要(rules/v1 · 2026-09-27 16:51):Organization-scoped, read-only access to EvalGate project, evaluation, run, and baseline evidence
这是模型对公开材料的总结,不是官方声明,请以原链内容为准。
这是模型对公开材料的总结,不是官方声明,请以原链内容为准。
接入信息
- 传输形态
- http
- 鉴权方式
- 鉴权未知
- 端点
https://evalgate--evalgate.run.tools
鉴权方式未标注,请核对官方文档后再接入——不要直接使用以下片段
{
"mcpServers": {
"EvalGate": {
"url": "https://evalgate--evalgate.run.tools"
}
}
}
能力清单
| 工具 | 说明 |
|---|---|
| project.inspect | Inspect the evaluations and project keys available in the authenticated organization. |
| project.plan | Return a non-mutating next-step plan for connecting a repository, evaluation, or trace source. |
| evaluations.list | List evaluations with a stable cursor for the organization. |
| runs.list | List evaluation runs with stable cursors and regression signals. |
| run.explain | Explain a run using its status, failed-case metadata, and evidence-lineage summary. |
| baseline.lineage | Show the published baseline anchor and its evidence lineage. |
| docs.search | Search the published OpenAPI operation catalog for relevant help. |
| connector.health | Show the latest connector-readiness reports for the organization. |
纠错与举报(发现条目失效、署名有误或涉及侵权?)
提交举报 / 纠错
侵权举报经核验成立后,我们会即时下线该条目并删除已存的内容副本。